Komawa Labarai
SamfuraAI Understanding takaitaccen bayani

PayU ta ƙaddamar da kariyar zamba ta AI don biyan katin kuɗi na duniya

PayU ya ce sabon samfurin sa na Kare Laifin Zartarwa yana amfani da kimanta haɗarin tushen AI da ingantaccen tabbaci don kare ƙwararrun ƴan kasuwa na Indiya daga wasu zamba na katin kan iyaka.

4 min readRead the linked source
Source-provided image accompanying PayU launches AI fraud protection for international card payments
Tushen tusheAn rubuta tushen tushe
Mawallafi
dqindia.com
Tushen hanyar haɗin gwiwa
dqindia.comhttps://www.dqindia.com/news/payu-launches-ai-fraud-protection-for-international-card-payments-12524928
Nau'in tushe
Tushen da aka haɗa - ba a kafa matsayin tushen farko ba.
MaganaFahimtar wannan a cikin daƙiƙa 60

Fara a nan

Mabuɗin sharuddan

Sirrin Artificial (AI)
Faɗin fage na tsarin gine-gine wanda ke aiwatar da ayyuka masu buƙatar sanin ƙima, tunani, harshe, ko yanke shawara.
Gwada kankaAI Model An Bayyana Tambayoyi

Me ya faru

DQ India reports that PayU launched Fraud Liability Protect (FLP), an AI-powered product for Indian merchants accepting international card payments. The system evaluates transaction and behavioural signals, applies different authentication levels according to assessed risk, and protects eligible merchants against certain fraud-related chargebacks. PayU says FLP integrates with PayU Checkout and is already being used by some merchants, including Zomato for international transactions. The company is positioning it toward small and medium-sized businesses in travel, online travel, airlines, e-commerce, quick commerce, and food technology. Exact eligibility, onboarding requirements, coverage exclusions, pricing, and broader availability are not reported.

According to DQ India, PayU unveiled Fraud Liability Protect at the Global Fintech Fest 2026 for Indian merchants accepting international card payments. PayU describes the product as using artificial intelligence and machine-learning-based risk assessment across multiple transaction and behavioural signals.

FLP is designed to route lower-risk transactions through less burdensome authentication while applying stronger authentication to higher-risk payments. It also offers eligible merchants protection against certain fraud-related chargebacks. The source does not specify the full eligibility criteria, coverage limits, pricing, or contractual terms.

PayU says FLP integrates with PayU Checkout and is already being used by some merchants. DQ India identifies Zomato as a user for international transactions and reports that an online travel merchant saw a 14% improvement in payment success rates and an 83% reduction in its fraud-to-sales ratio after adoption. PayU also claims merchants using the product are seeing an approximately 4–5% improvement in international card payment success rates.

Bayanan tushe: dqindia.com ↗

Me ya sa yake da mahimmanci

Cross-border payment controls must balance fraud prevention against the risk that additional authentication causes legitimate transactions to fail. If PayU’s reported results hold beyond the cited merchants, risk-based authentication could offer a practical way to reduce friction while limiting merchants’ exposure to eligible fraud chargebacks. The product also illustrates how payment providers are applying AI to transaction-level decisions as fraud tactics become more sophisticated. However, the performance figures are company-reported and were not independently verified by DQ India or in the supplied material. No methodology, comparison baseline, sample size, measurement period, or definition of the covered fraud claims is provided, so the reported improvements cannot yet be generalized to all merchants or transaction types.

International payment declines can directly affect revenue for travel, commerce, and food businesses. A system that adjusts authentication to transaction risk could reduce unnecessary friction while preserving stronger checks for payments considered more dangerous.

The product is a concrete commercial deployment of AI in payment-risk decisioning, with potential implications for merchant losses, customer checkout experience, and the allocation of fraud liability. Its relevance is strongest for merchants already using PayU’s payment infrastructure.

All outcome figures in the supplied report are attributed to PayU. Independent confirmation, testing results, methodology, sample sizes, time periods, and evidence that the results apply broadly are not available.

Interactive Mechanism

Ingantacciyar hanyar sadarwa: Yadda A zahiri yake Aiki

Bincika fasahar da ke bayan wannan ci gaban ta hanyar mu'amala.

Agent Lifecycle Stage:
1
User Intent & Planning: "Audit customer refund request #4092 and settle payment."
2
Tool Calling: Emits structured JSON call crm_get_transaction(id='4092').
3
Guardrail & Verification:🛡️ Paused: High-value action requires human operator sign-off.
4
Final Settlement: Refund recorded, email receipt dispatched, and audit log stored.
Core takeaway: An AI agent is not just a language model—it is a closed loop of planning, tool invocation, and environment feedback. Production systems require self-healing retries and strict human approval guardrails.
Duba ra'ayi na hulɗa+10 Points
AI Models Explained Quiz

Which component of an AI application is the machine-learning model itself?

Abin kallo na gaba

The key questions are whether FLP becomes broadly available through PayU Checkout, which merchants and transactions qualify for liability protection, and what exclusions or fees apply. PayU’s reported 4–5% improvement in international card payment success rates and one travel merchant’s reported 14% improvement and 83% reduction in fraud-to-sales ratio warrant independent validation across larger samples. Merchants should also watch how PayU handles false declines, customer authentication, privacy and data governance, and disputes over whether a chargeback qualifies for protection. The supplied report does not establish that the system outperforms other fraud tools or that its AI decisions are independently audited.

PayU’s wider rollout, merchant eligibility, pricing, liability exclusions, and dispute process remain unknown. The report establishes use by some merchants but does not establish general availability.

Independent measurements should clarify whether the claimed approval-rate gains persist without increasing fraud, false approvals, authentication failures, or customer complaints.

The source does not describe the model architecture, data retention, privacy safeguards, human review, or audit process used for FLP’s risk decisions.

Jagorori masu alaƙa & tambayoyin tambayoyi

AI Model ya bayyanaƊa'a ta AIMakomar AIGwada abin da kuka sani - gwada gwajin AI kyautaNemo kalmar AI a cikin ƙamus ɗin muBi samfurin AI na sakin tracker
An sami wannan yana da amfani?